Behaviour Suite for Reinforcement Learning.
Ian OsbandYotam DoronMatteo HesselJohn AslanidesEren SezenerAndre SaraivaKatrina McKinneyTor LattimoreCsaba SzepesváriSatinder SinghBenjamin Van RoyRichard S. SuttonDavid SilverHado van HasseltPublished in: CoRR (2019)
Keyphrases
- reinforcement learning
- reward function
- function approximation
- learning algorithm
- state space
- user behaviour
- model free
- neural network
- transition model
- optimal policy
- direct policy search
- continuous state
- control problems
- reinforcement learning algorithms
- learning classifier systems
- optimal control
- transfer learning
- real time
- learning process
- machine learning
- evolutionary algorithm
- temporal difference
- case study
- knowledge base
- social networks
- information retrieval
- databases